Context Tree for Adaptive Session-based Recommendation
This addresses the problem of adaptive recommendations for anonymous sessions in domains like news and forums, but it is incremental as it benchmarks a new method against existing ones.
The paper tackled session-based recommendation with continuously arriving new items, benchmarking a nonparametric context tree method against state-of-the-art approaches. Results showed that CT outperformed recurrent neural networks and heuristic-based nearest neighbor methods in most configurations and datasets, with better adaptation to changes and efficient running times.
There has been growing interests in recent years from both practical and research perspectives for session-based recommendation tasks as long-term user profiles do not often exist in many real-life recommendation applications. In this case, recommendations for user's immediate next actions need to be generated based on patterns in anonymous short sessions. An often overlooked aspect is that new items with limited observations arrive continuously in many domains (e.g. news and discussion forums). Therefore, recommendations need to be adaptive to such frequent changes. In this paper, we benchmark a new nonparametric method called context tree (CT) against various state-of-the-art methods on extensive datasets for session-based recommendation task. Apart from the standard static evaluation protocol adopted by previous literatures, we include an adaptive configuration to mimic the situation when new items with limited observations arrives continuously. Our results show that CT outperforms two best-performing approaches (recurrent neural network; heuristic-based nearest neighbor) in majority of the tested configurations and datasets. We analyze reasons for this and demonstrate that it is because of the better adaptation to changes in the domain, as well as the remarkable capability to learn static sequential patterns. Moreover, our running time analysis illustrates the efficiency of using CT as other nonparametric methods.